Skip to content
2000
Volume 20, Issue 1
  • ISSN: 1573-4056
  • E-ISSN: 1875-6603

Abstract

Background

Non-invasive bio-diagnostics are essential for providing patients with safer treatment. In this subject, significant growth is attained for non-invasive anaemia detection in terms of Hb concentration by means of spectroscopic and image analysis. The lower satisfaction rate is found due to inconsistent results in various patient settings.

Objective

This observational study aims to present an adaptable point-of-care Near-Infrared (NIR) spectrophotometric approach with a constructive Machine Learning (ML) algorithm for monitoring Haemoglobin (Hb) concentration by considering dominating influencing factors into account.

Methods

To accomplish this objective, 121 subjects (19.2-55.4 years) were enrolled in the study, having a wide range of Hb concentrations (8.2-17.4 g/dL) obtained from two standard Laboratory analyzers. To inspect the performance, the unique dimensionality reduction approaches are applied with numerous regression models using 5-fold cross-validation.

Results

The optimum accuracy is found using support vector regression (SVR) and mutual information having 3 independent features . Pearson correlation (r)= 0.79, standard deviation (SD)= 1.07 g/dL, bias=-0.13 g/dL and limits of agreement (LoA)=-2.22 to 1.97 g/dL. Additionally, comparability between two standard laboratory analyzers is found as; r=0.97, SD=0.50 g/dL, bias=0.21 g/dL, and LoA= -0.77 to 1.19 g/dL.

Conclusion

The precision of ±1 g/dL in 5-fold cross-validation ensures the same performance irrespective of different age groups, gender, BMI, smoking level, drinking level, and skin type. The outcomes with the offered NIR sensing system and an exclusive ML algorithm can accelerate its’ requirement at remote locative rural areas and critical care units where continuous Hb monitoring is compulsory.

This is an open access article distributed under the terms of the Creative Commons Attribution 4.0 International Public License (CC-BY 4.0), a copy of which is available at: https://creativecommons.org/licenses/by/4.0/legalcode. This license permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Loading

Article metrics loading...

/content/journals/cmir/10.2174/0115734056271761231204093832
2024-01-01
2025-07-09
The full text of this item is not currently available.

References

  1. Hematology Disorders | UCLA HealthAvailable from:https://www.uclahealth.org/mattel/pediatric-hematology-oncology/hematology-disorders (Accessed: Aug. 18, 2021)
  2. TrR. Kumar LilhoreU. SimaiyaS. KaurA. HamdiM. Predictive analysis of heart diseases with machine learning approaches.Malaysian J Comput Sci202211324810.22452/mjcs.sp2022no1.10
    [Google Scholar]
  3. ChenL.Y. HuangC.C. ChenW.Y. LinH.J. ChangH.T. Using photoluminescent gold nanodots to detect hemoglobin in diluted blood samples.Biosens. Bioelectron.2013431384410.1016/j.bios.2012.11.03423274195
    [Google Scholar]
  4. FairbanksV.F. TefferiA. Normal ranges for packed cell volume and hemoglobin concentration in adults: relevance to ‘apparent polycythemia’.Eur. J. Haematol.200065528529610.1034/j.1600‑0609.2000.065005285.x11092458
    [Google Scholar]
  5. van SwelmR.P.L. WetzelsJ.F.M. SwinkelsD.W. The multifaceted role of iron in renal health and disease.Nat. Rev. Nephrol.2020162779810.1038/s41581‑019‑0197‑531554933
    [Google Scholar]
  6. MemmoloP. ApreaG. BiancoV. RussoR. AndolfoI. MugnanoM. MerolaF. MiccioL. IolasconA. FerraroP. Differential diagnosis of hereditary anemias from a fraction of blood drop by digital holography and hierarchical machine learning.Biosens. Bioelectron.202220111394510.1016/j.bios.2021.11394535032844
    [Google Scholar]
  7. HasanM.K. AzizM.H. ZarifM.I.I. HasanM. HashemM.M.A. GuhaS. LoveR.R. AhamedS. Noninvasive hemoglobin level prediction in a mobile phone environment: State of the art review and recommendations.JMIR Mhealth Uhealth202194e1680610.2196/1680633830065
    [Google Scholar]
  8. LozoffB. CorapciF. BurdenM.J. KacirotiN. Angulo-BarrosoR. SazawalS. BlackM. Preschool-aged children with iron deficiency anemia show altered affect and behavior.J. Nutr.2007137368368910.1093/jn/137.3.68317311960
    [Google Scholar]
  9. DaruJ. ZamoraJ. Fernández-FélixB.M. VogelJ. OladapoO.T. MorisakiN. TunçalpÖ. TorloniM.R. MittalS. JayaratneK. LumbiganonP. TogoobaatarG. ThangaratinamS. KhanK.S. Risk of maternal mortality in women with severe anaemia during pregnancy and post partum: a multilevel analysis.Lancet Glob. Health201865e548e55410.1016/S2214‑109X(18)30078‑029571592
    [Google Scholar]
  10. World Health OrganizationWorldwide prevalence of anaemia 1993-2005: WHO global database on anaemia.2008Available from:https://www.who.int/publications/i/item/9789241596657
  11. Tallqvist’s Hämoglobin scale - Science History Institute Digital CollectionsAvailable from:https://digital.sciencehistory.org/works/3n203z971 (Accessed: Jun. 28, 2020)
  12. StoneJ.E. SimmonsW.K. JutsumP.J. GurneyJ.M. An evaluation of methods of screening for anaemia.Bull. World Health Organ.19846211151206609016
    [Google Scholar]
  13. van LerbergheW. KeegelsG. CornelisG. AnconaC. MangelschotsE. van BalenH. Haemoglobin measurement: the reliability of some simple techniques for use in a primary health care setting.Bull. World Health Organ.19836169579656609012
    [Google Scholar]
  14. SahliH. KinnicuttF.P. PotterN.B. A Treatise on Diagnostic Methods of Examination.W.B. Saunders Company1907
    [Google Scholar]
  15. von SchenckH. FalkenssonM. LundbergB. Evaluation of “HemoCue,” a new device for determining hemoglobin.Clin. Chem.198632352652910.1093/clinchem/32.3.5263948400
    [Google Scholar]
  16. DhingraN. WHO guidelines on drawing blood: Best practices in phlebotomy.2010Available from:https://books.google.co.in/books?id=ltDWoAEACAAJ
  17. Best Practices for Injections and Related Procedures Toolkit.WHO2010
    [Google Scholar]
  18. AnR. HuangY. ManY. ValentineR.W. KucukalE. GorekeU. SekyondaZ. PicconeC. Owusu-AnsahA. AhujaS. LittleJ.A. GurkanU.A. Emerging point-of-care technologies for anemia detection.Lab Chip202121101843186510.1039/D0LC01235A33881041
    [Google Scholar]
  19. SarkarP.K. PalS. PolleyN. AichR. AdhikariA. HalderA. ChakrabartiS. ChakrabartiP. PalS.K. Development and validation of a noncontact spectroscopic device for hemoglobin estimation at point-of-care.J. Biomed. Opt.201722505500610.1117/1.JBO.22.5.05500628510622
    [Google Scholar]
  20. JeonK.J. KimS.J. ParkK.K. KimJ.W. YoonG. Noninvasive total hemoglobin measurement.J. Biomed. Opt.200271455010.1117/1.142704711818011
    [Google Scholar]
  21. FengX. LiG. YuH. WangS. YiX. LinL. Wavelength selection for portable noninvasive blood component measurement system based on spectral difference coefficient and dynamic spectrum.Spectrochim. Acta A Mol. Biomol. Spectrosc.2018193404610.1016/j.saa.2017.10.06329223052
    [Google Scholar]
  22. AcharyaS. SwaminathanD. DasS. KansaraK. ChakrabortyS. Kumar RD. FrancisT. AatreK.R. Non-invasive estimation of hemoglobin using a multi-model stacking regressor.IEEE J. Biomed. Health Inform.20202461717172610.1109/JBHI.2019.295455331751256
    [Google Scholar]
  23. KumarR.D. GuruprasadS. KansaraK. RaoK.N.R. MohanM. ReddyM.R. PrabhuU.H. PrakashP. ChakrabortyS. DasS. MadhusoodananK.N. A novel noninvasive hemoglobin sensing device for anemia screening.IEEE Sens. J.20212113153181532910.1109/JSEN.2021.3070971
    [Google Scholar]
  24. KavsaoğluA.R. PolatK. HariharanM. Non-invasive prediction of hemoglobin level using machine learning techniques with the PPG signal’s characteristics features.Appl. Soft Comput.20153798399110.1016/j.asoc.2015.04.008
    [Google Scholar]
  25. ManninoR.G. MyersD.R. TyburskiE.A. CarusoC. BoudreauxJ. LeongT. CliffordG.D. LamW.A. Smartphone app for non-invasive detection of anemia using only patient-sourced photos.Nat. Commun.201891492410.1038/s41467‑018‑07262‑230514831
    [Google Scholar]
  26. KumarY. DograA. ShawV. KaushikA. KumarS. NIR-based sensing system for non-Invasive detection of Hemoglobin for point-of-care applications.Curr Med Imaging2021185532545
    [Google Scholar]
  27. EdwardsP. ZhangC. ZhangB. HongX. NagarajanV.K. YuB. LiuZ. Smartphone based optical spectrometer for diffusive reflectance spectroscopic measurement of hemoglobin.Sci. Rep.2017711222410.1038/s41598‑017‑12482‑528939898
    [Google Scholar]
  28. McMurdyJ.W. JayG.D. SunerS. TrespalaciosF.M. CrawfordG.P. Diffuse reflectance spectra of the palpebral conjunctiva and its utility as a noninvasive indicator of total hemoglobin.J. Biomed. Opt.200611101401910.1117/1.216796716526896
    [Google Scholar]
  29. JayG.D. Point-of-care noninvasive hemoglobin determination using fiber optic reflectance spectroscopy.29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.Lyon, France22-26 Aug20072932293510.1109/IEMBS.2007.4352943
    [Google Scholar]
  30. SunerS. CrawfordG. McMurdyJ. JayG. Non-invasive determination of hemoglobin by digital photography of palpebral conjunctiva.J. Emerg. Med.200733210511110.1016/j.jemermed.2007.02.01117692757
    [Google Scholar]
  31. DimauroG. CaivanoD. GirardiF. A new method and a non-invasive device to estimate anemia based on digital images of the conjunctiva.IEEE Access20186469684697510.1109/ACCESS.2018.2867110
    [Google Scholar]
  32. SunerS. RaynerJ. OzturanI.U. HoganG. MeehanC.P. ChambersA.B. BairdJ. JayG.D. Prediction of anemia and estimation of hemoglobin concentration using a smartphone camera.PLoS One2021167e025349510.1371/journal.pone.025349534260592
    [Google Scholar]
  33. CollingsS. ThompsonO. HirstE. GoossensL. GeorgeA. WeinkoveR. Non-invasive detection of anaemia using digital photographs of the conjunctiva.PLoS One2016114e015328610.1371/journal.pone.015328627070544
    [Google Scholar]
  34. ChenZ. QinH. GeW. LiS. Research on a non-invasive hemoglobin measurement system based on four-wavelength photoplethysmography.Electronics2023261346
    [Google Scholar]
  35. DimauroG. GrisetaM.E. CamporealeM.G. ClementeF. GuariniA. MagliettaR. An intelligent non-invasive system for automated diagnosis of anemia exploiting a novel dataset.Artif. Intell. Med.202313610247710.1016/j.artmed.2022.10247736710064
    [Google Scholar]
  36. HuX. A new, feasible, and convenient method based on semantic segmentation and deep learning for hemoglobin monitoring.Front Med202310115199610.3389/fmed.2023.1151996
    [Google Scholar]
  37. MacknetM.R. AllardM. ApplegateR.L.II RookJ. The accuracy of noninvasive and continuous total hemoglobin measurement by pulse CO-Oximetry in human subjects undergoing hemodilution.Anesth. Analg.201011161424142610.1213/ANE.0b013e3181fc74b921048100
    [Google Scholar]
  38. RaikhelM. Accuracy of noninvasive and invasive point-of-care total blood hemoglobin measurement in an outpatient setting.Postgrad. Med.2012124425025510.3810/pgm.2012.07.258422913913
    [Google Scholar]
  39. HadarE. RabanO. BouganimT. Tenenbaum-GavishK. HodM. Precision and accuracy of noninvasive hemoglobin measurements during pregnancy.J. Matern. Fetal Neonatal Med.201225122503250610.3109/14767058.2012.70445322746256
    [Google Scholar]
  40. BelardinelliA. BenniM. TazzariP.L. PagliaroP. Noninvasive methods for haemoglobin screening in prospective blood donors.Vox Sang.2013105211612010.1111/vox.1203323600766
    [Google Scholar]
  41. IsosuT. ObaraS. HosonoA. OhashiS. NakanoY. ImaizumiT. MogamiM. MurakawaM. Validation of continuous and noninvasive hemoglobin monitoring by pulse CO-oximetry in Japanese surgical patients.J. Clin. Monit. Comput.2013271556010.1007/s10877‑012‑9397‑222986804
    [Google Scholar]
  42. KhalafallahA.A. ChilversC.R. ThomasM. ChilversC.M. SextonM. VialleM. RobertsonI.K. Usefulness of non-invasive spectrophotometric haemoglobin estimation for detecting low haemoglobin levels when compared with a standard laboratory assay for preoperative assessment.Br. J. Anaesth.2015114466967610.1093/bja/aeu40325501721
    [Google Scholar]
  43. BridgesE. HatzfeldJ.J. Noninvasive continuous hemoglobin monitoring in combat casualties: a pilot study.Shock2016463S556010.1097/SHK.000000000000065427501120
    [Google Scholar]
  44. GamalM. AbdelhamidB. ZakariaD. DayemO.A.E. RadyA. FawzyM. HasaninA. Evaluation of noninvasive hemoglobin monitoring in trauma patients with low hemoglobin levels.Shock201849215015310.1097/SHK.000000000000094928727608
    [Google Scholar]
  45. TsueiB.J. HansemanD.J. BlakemanM.J. BlakemanT.C. YangS.H. BransonR.D. GerlachT.W. Accuracy of noninvasive hemoglobin monitoring in patients at risk for hemorrhage.J. Trauma Acute Care Surg.2014773S134S13910.1097/TA.000000000000032625159346
    [Google Scholar]
  46. AwadaW.N. MohmouedM.F. RadwanT.M. HussienG.Z. ElkadyH.W. Continuous and noninvasive hemoglobin monitoring reduces red blood cell transfusion during neurosurgery: A prospective cohort study.J. Clin. Monit. Comput.201529673374010.1007/s10877‑015‑9660‑425649717
    [Google Scholar]
  47. GuptaN. KulkarniA. BhargavaA.K. PrakashA. GuptaN. Utility of non-invasive haemoglobin monitoring in oncosurgery patients.Indian J. Anaesth.201761754354810.4103/ija.IJA_707_1628794525
    [Google Scholar]
  48. BruellsC.S. MenonA.K. RossaintR. GoetzenichA. CzaplikM. ZorembaN. AutschbachR. SchaelteG. Accuracy of the Masimo Pronto-7® system in patients with left ventricular assist device.J. Cardiothorac. Surg.20138115910.1186/1749‑8090‑8‑15923800231
    [Google Scholar]
  49. Radical-7 ® Pulse CO-OximeterAvailable from:https://www.masimo.com/siteassets/us/documents/pdf/plm-10014b_product_information_radical-7_us.pdf (Accessed: Aug. 21, 2021)
  50. Pronto Pulse CO- CoximeterAvailable from:https://www.masimo.com/siteassets/us/documents/pdf/plm-10077b_product_information_pronto.pdf (Accessed: May 12, 2020)
  51. Masimo - Radical-7Available from:https://www.masimo.com/products/continuous/radical-7/ (Accessed: May 12, 2020)
  52. Masimo CorporationMasimo - Pronto2020
    [Google Scholar]
  53. Sysmex CorporationSysmex Launches New ASTRIM FIT Product for Noninvasive Measurement of Estimated Hemoglobin Levels | Sysmex.Available from:https://www.sysmex.co.jp/en/news/2014/140115.html (Accessed: Aug. 21, 2021)
  54. Smart HB | Hemoglobin Monitor | Non Invasive Hemoglobin TestingAvailable from:http://tech4lifeenterprises.com/smart-hb/ (Accessed: Aug. 21, 2021)
  55. KumarY. DograA. KaushikA. KumarS. Progressive evaluation in spectroscopic sensors for non-invasive blood haemoglobin analysis-A review.Physiol. Meas.202134883473
    [Google Scholar]
  56. Al-AliC. Multiple wavelength sensor attachment.W.O. Patent 2006115580A22009
  57. Al-AliA. IndorfK.W. Total hemoglobin screening sensor.U.S. Patent 10231657B22019
  58. HT-320 - 3 Part - AGD Biomedicals Pvt LtdAvailable from:https://www.agdbio.com/products/ht-320/ (Accessed: Nov. 02, 2021)
  59. CompoLab TS - Fresenius Kabi IndiaAvailable from:https://www.fresenius-kabi.com/in/products/compolab-ts (Accessed: Nov. 02, 2021)
  60. Sklearn.model_selection.KFold — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.model_selection.KFold.html (Accessed: Nov. 03, 2021)
  61. sklearn.feature_selection.mutual_info_regression — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.mutual_info_regression.html#r37d39d7589e2-1 (Accessed: Nov. 11, 2021)
  62. Elements of Information Theory - Google BooksAvailable from:https://www.google.co.in/books/edition/Elements_of_Information_Theory/VWq5GG6ycxMC?hl=en&gbpv=1&dq=mutual+information&printsec=frontcover (Accessed: Nov. 07, 2022. )
  63. Variance DefinitionAvailable from:https://www.investopedia.com/terms/v/variance.asp (Accessed: Dec. 25, 2021)
  64. sklearn.feature_selection.VarianceThreshold — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.VarianceThreshold.html (Accessed: Nov. 03, 2021)
  65. sklearn.feature_selection.SelectFromModel — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SelectFromModel.html (Accessed: Nov. 03, 2021)
  66. sklearn.feature_selection.SequentialFeatureSelector — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.feature_selection.SequentialFeatureSelector.html (Accessed: Nov. 13, 2021)
  67. 1.13. Feature selection — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/feature_selection.html#sequential-feature-selection (Accessed: Nov. 13, 2021)
  68. Forward Feature Selection | Implementation of Forward Feature SelectionAvailable from:https://www.analyticsvidhya.com/blog/2021/04/forward-feature-selection-and-its-implementation/ (Accessed: Dec. 27, 2021)
  69. Backward Feature Elimination and its ImplementationAvailable from:https://www.analyticsvidhya.com/blog/2021/04/backward-feature-elimination-and-its-implementation/ (Accessed: Dec. 27, 2021)
  70. EldeebS. SusamB. AkcakayaM. Trial by trial EEG based BCI for distress versus non distress classification in individuals with ASD.Sci Rep2021116000
    [Google Scholar]
  71. Sklearn.decomposition.PCA — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.decomposition.PCA.html (Accessed: Nov. 13, 2021)
  72. Principal component analysisAvailable from:https://en.wikipedia.org/wiki/Principal_component_analysis (Accessed: Nov. 08, 2022)
  73. VermaK. BhardwajS. AryaR. IslamU. BhushanM. Latest tools for data mining and machine learning.IJITEE20198S91823
    [Google Scholar]
  74. WangC. WuP. YanL. YeZ. ChenH. LingH. Image classification based on principal component analysis optimized generative adversarial networks.Multimed Tools Appl20208069687970110.1109/IDAACS‑SWS50031.2020.9297081
    [Google Scholar]
  75. VijayG. S. PaiS. P. SriramN. S. RaoR. B. K. N. Radial basis function neural network based comparison of dimensionality reduction techniques for effective bearing diagnostics.Proc. Instit. Mech. Eng., Part J : J. Eng. Tribol.2012227664065310.1177/1350650112464927
    [Google Scholar]
  76. Polynomial Regression CalculatorAvailable from:https://www.omnicalculator.com/statistics/polynomial-regression (Accessed: Nov. 01, 2022)
  77. LilhoreU. PoongodiM. KaurA. Hybrid model for detection of cervical cancer using causal analysis and machine learning techniques.Comput Math Methods Med202220224688327
    [Google Scholar]
  78. 1.10. Decision Trees — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/tree.html (Accessed: Dec. 19, 2021)
  79. sklearn.tree.DecisionTreeRegressor — scikit-learn 1.0.1Available from:https://scikit-learn.org/stable/modules/generated/sklearn.tree.DecisionTreeRegressor.html#sklearn.tree.DecisionTreeRegressor (Accessed: Dec. 19, 2021)
  80. An Introduction to Support Vector Regression (SVR) | by Tom Sharp | Towards Data ScienceAvailable from:https://towardsdatascience.com/an-introduction-to-support-vector-regression-svr-a3ebc1672c2 (Accessed: Nov. 06, 2022)
  81. Support Vector RegressionAvailable from:https://www.saedsayad.com/support_vector_machine_reg.htm (Accessed: Nov. 06, 2022.)
  82. sklearn.svm.SVR — scikit-learn 1.1.3Available from:https://scikit-learn.org/stable/modules/generated/sklearn.svm.SVR.html (Accessed: Nov. 06, 2022)
  83. Regression and CorrelationAvailable from:http://faculty.washington.edu/ddbrewer/s231/s231regr.htm (Accessed: Aug. 11, 2020)
  84. NoiriE. KobayashiN. TakamuraY. IijimaT. TakagiT. DoiK. NakaoA. YamamotoT. TakedaS. FujitaT. Pulse total-hemoglobinometer provides accurate noninvasive monitoring.Crit. Care Med.20053312E283110.1097/01.CCM.0000190430.96750.5116352948
    [Google Scholar]
  85. HaggenmüllerV. Smartphone-based point-of-care anemia screening in rural Bihar in India.Commun. Med.20233111010.1038/s43856‑023‑00267‑z
    [Google Scholar]
  86. GhosalS. DasD. sHEMO: Smartphone spectroscopy for blood hemoglobin level monitoring in smart anemia-care.IEEE Sensors J.20209911
    [Google Scholar]
  87. YiX. LiG. LinL. Noninvasive hemoglobin measurement using dynamic spectrum.Rev. Sci. Instrum.201788808310910.1063/1.499897828863662
    [Google Scholar]
  88. HasanM.K. AhamedS.I. LoveR.R. Method and Apparatus for Non-Invasive Hemoglobin Level Prediction.Google Patents2021
    [Google Scholar]
  89. IlyaF. Method and device for non-invasive measurements in a subject.E.P. Patent 1942790B12006
  90. BenderJ.E. ShangA.B. MorettiE.W. YuB. RichardsL.M. RamanujamN. Noninvasive monitoring of tissue hemoglobin using UV-VIS diffuse reflectance spectroscopy: A pilot study.Opt. Express20091726233962340910.1364/OE.17.02339620052047
    [Google Scholar]
  91. Bin NoorN. AnwarM.S. DeyM. An Efficient Technique of Hemoglobin Level Screening Using Machine Learning Algorithms.4th International Conference on Electrical Information and Communication Technology (EICT).Khulna, Bangladesh20-22 Dec2019
    [Google Scholar]
  92. WangE.J. LiW. ZhuJ. RanaR. PatelS.N. Noninvasive hemoglobin measurement using unmodified smartphone camera and white flash.Annu Int Conf IEEE Eng Med Biol Soc201720172333233610.1109/EMBC.2017.8037323
    [Google Scholar]
/content/journals/cmir/10.2174/0115734056271761231204093832
Loading
/content/journals/cmir/10.2174/0115734056271761231204093832
Loading

Data & Media loading...

Supplements

The supplementary material from S1 to S19 is provided with the article.

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error
Please enter a valid_number test